A Tale of Two Desolvation Potentials: An Investigation of Protein Behavior Under High Hydrostatic Pressure. (arXiv:1911.06692v1 [q-bio.BM])

Hydrostatic pressure is a common perturbation to probe the conformations of proteins. There are two common forms of pressure dependent potentials of mean force (PMFs) derived from hydrophobic molecules available for the coarse grained molecular simulations of protein folding and unfolding under hydrostatic pressure. Although both PMF includes a desolvation barrier separating the well of…

Explicit-Blurred Memory Network for Analyzing Patient Electronic Health Records. (arXiv:1911.06472v1 [cs.LG])

In recent years, we have witnessed an increased interest in temporal modeling of patient records from large scale Electronic Health Records (EHR). While simpler RNN models have been used for such problems, memory networks, which in other domains were found to generalize well, are underutilized. Traditional memory networks involve diffused and non-linear operations where influence…

Sequential Recommendation with Relation-Aware Kernelized Self-Attention. (arXiv:1911.06478v1 [cs.LG])

Recent studies identified that sequential Recommendation is improved by the attention mechanism. By following this development, we propose Relation-Aware Kernelized Self-Attention (RKSA) adopting a self-attention mechanism of the Transformer with augmentation of a probabilistic model. The original self-attention of Transformer is a deterministic measure without relation-awareness. Therefore, we introduce a latent space to the self-attention,…

On Model Robustness Against Adversarial Examples. (arXiv:1911.06479v1 [cs.LG])

We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the robustness issue from the perspective of stability of the loss function in the small neighborhood of natural examples. We propose to…

OpenLORIS-Object: A Dataset and Benchmark towards Lifelong Object Recognition. (arXiv:1911.06487v1 [cs.CV])

The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks. Fully retraining models…

Single View Distortion Correction using Semantic Guidance. (arXiv:1911.06505v1 [cs.CV])

Most distortion correction methods focus on simple forms of distortion, such as radial or linear distortions. These works undistort images either based on measurements in the presence of a calibration grid, or use multiple views to find point correspondences and predict distortion parameters. When possible distortions are more complex, e.g. in the case of a…

Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice. (arXiv:1911.06515v1 [stat.ML])

Recent work has shown that deep generative models assign higher likelihood to out-of-distribution inputs than to training data. We show that a factor underlying this phenomenon is a mismatch between the nature of the prior distribution and that of the data distribution, a problem found in widely used deep generative models such as VAEs and…

Toward Scalable Many-Body Calculations for Nuclear Open Quantum Systems using the Gamow Shell Model. (arXiv:1911.06494v1 [physics.comp-ph])

Drip-line nuclei have very different properties from those of the valley of stability, as they are weakly bound and resonant. Therefore, the models devised for stable nuclei can no longer be applied therein. Hence, a new theoretical tool, the Gamow Shell Model (GSM), has been developed to study the many-body states occurring at the limits…

Characterization of ionization injection in gas mixtures irradiated by sub-petawatt class laser pulses. (arXiv:1911.06512v1 [physics.plasm-ph])

Effects of ionization injection in low and high Z gas mixtures for the laser wake field acceleration of electrons are analyzed with the use of balance equations and particle-in-cell simulations via test probe particle trajectories in realistic plasma fields and direct simulations of charge loading during the ionization process. It is shown that electrons appearing…